ButterChicken98 commited on
Commit
123363c
·
verified ·
1 Parent(s): ca99061

End of training

Browse files
Files changed (35) hide show
  1. .gitattributes +1 -0
  2. README.md +68 -0
  3. checkpoint-3000/optimizer.bin +3 -0
  4. checkpoint-3000/random_states_0.pkl +3 -0
  5. checkpoint-3000/scaler.pt +3 -0
  6. checkpoint-3000/scheduler.bin +3 -0
  7. checkpoint-3000/unet/config.json +73 -0
  8. checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-4000/optimizer.bin +3 -0
  10. checkpoint-4000/random_states_0.pkl +3 -0
  11. checkpoint-4000/scaler.pt +3 -0
  12. checkpoint-4000/scheduler.bin +3 -0
  13. checkpoint-4000/unet/config.json +73 -0
  14. checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
  15. checkpoint-5000/optimizer.bin +3 -0
  16. checkpoint-5000/random_states_0.pkl +3 -0
  17. checkpoint-5000/scaler.pt +3 -0
  18. checkpoint-5000/scheduler.bin +3 -0
  19. checkpoint-5000/unet/config.json +73 -0
  20. checkpoint-5000/unet/diffusion_pytorch_model.safetensors +3 -0
  21. feature_extractor/preprocessor_config.json +27 -0
  22. logs/text2image-fine-tune/1767299243.525676/events.out.tfevents.1767299243.admin---AgriEdgeX-Research.3517659.1 +3 -0
  23. logs/text2image-fine-tune/1767299243.5278287/hparams.yml +56 -0
  24. logs/text2image-fine-tune/events.out.tfevents.1767299241.admin---AgriEdgeX-Research.3517659.0 +3 -0
  25. model_index.json +38 -0
  26. scheduler/scheduler_config.json +15 -0
  27. text_encoder/config.json +24 -0
  28. text_encoder/model.safetensors +3 -0
  29. tokenizer/tokenizer.json +0 -0
  30. tokenizer/tokenizer_config.json +13 -0
  31. unet/config.json +73 -0
  32. unet/diffusion_pytorch_model.safetensors +3 -0
  33. vae/config.json +38 -0
  34. vae/diffusion_pytorch_model.safetensors +3 -0
  35. val_imgs_grid.png +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Manojb/stable-diffusion-2-1-base
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - diffusers-training
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+
18
+ # Text-to-image finetuning - ButterChicken98/soy_qwen_bact_v2
19
+
20
+ This pipeline was finetuned from **Manojb/stable-diffusion-2-1-base** on the **ButterChicken98/soyabean_bact_puls_plus_healthy_Qwen_Detailed** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A photo of a soybean leaf with Early stage Bacterial Pustule, showing small, yellowish-brown lesions with a water-soaked appearance.']:
21
+
22
+ ![val_imgs_grid](./val_imgs_grid.png)
23
+
24
+
25
+ ## Pipeline usage
26
+
27
+ You can use the pipeline like so:
28
+
29
+ ```python
30
+ from diffusers import DiffusionPipeline
31
+ import torch
32
+
33
+ pipeline = DiffusionPipeline.from_pretrained("ButterChicken98/soy_qwen_bact_v2", torch_dtype=torch.float16)
34
+ prompt = "A photo of a soybean leaf with Early stage Bacterial Pustule, showing small, yellowish-brown lesions with a water-soaked appearance."
35
+ image = pipeline(prompt).images[0]
36
+ image.save("my_image.png")
37
+ ```
38
+
39
+ ## Training info
40
+
41
+ These are the key hyperparameters used during training:
42
+
43
+ * Epochs: 29
44
+ * Learning rate: 1e-05
45
+ * Batch size: 8
46
+ * Gradient accumulation steps: 1
47
+ * Image resolution: 512
48
+ * Mixed-precision: fp16
49
+
50
+
51
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/butterchicken-iit-indore/text2image-fine-tune/runs/hvt7i83s).
52
+
53
+
54
+ ## Intended uses & limitations
55
+
56
+ #### How to use
57
+
58
+ ```python
59
+ # TODO: add an example code snippet for running this diffusion pipeline
60
+ ```
61
+
62
+ #### Limitations and bias
63
+
64
+ [TODO: provide examples of latent issues and potential remediations]
65
+
66
+ ## Training details
67
+
68
+ [TODO: describe the data used to train the model]
checkpoint-3000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339ea56bf79bbca0359e0feff308a7c5b25362ae504c6e997c742ad5fb9549d0
3
+ size 6927874725
checkpoint-3000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae39dd55574172a5329e9ed65a683188d0ef5add1e3bf15075a4472349a57b2
3
+ size 14821
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
3
+ size 1383
checkpoint-3000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02e9f17ce277518998a9e4d19ad84caf30db9f1d981277dab1d182ec06d87f2
3
+ size 1401
checkpoint-3000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-3000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f303d38fc8abef9f80601d8d50738e799c6e9673dfa129bf5858e427af43ffc
3
+ size 3463726504
checkpoint-4000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5d1f6b7b482003ebc4a3a581458a4d7898795c495523762167c4ab2dd5b270
3
+ size 6927874725
checkpoint-4000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb05fff1b89e04cc159117a7b00e433cd80b292b3c2ddbf25b6bd9e5cbf7263
3
+ size 14821
checkpoint-4000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
3
+ size 1383
checkpoint-4000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf8d991cc0a7bf66ce6dd76db8fbcf166033896cb31e5e3f7ee7309f6bc1759
3
+ size 1401
checkpoint-4000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-4000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18c1f47ea4e993f3db8481ff0d14a762ccef06af898f0382b3be7e7af3ec6aa
3
+ size 3463726504
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dca9573730fee7398bc40fc33abdb9f35d8004c62cbfa4d9301e6594b65996
3
+ size 6927874725
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4288fc2d93334c275b3406bc28c3a3d003db9471d68ce24a33cb0ca5b35a9
3
+ size 14821
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
+ size 1383
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8089318ecef721d068a0f7d4d2d22bd54d376566c7d530413da298438031bd
3
+ size 1401
checkpoint-5000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
checkpoint-5000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f300063de8fcd9e9b36595bc7b7cdfa55b1094b8adc44667dc13f96e76a71f1e
3
+ size 3463726504
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
logs/text2image-fine-tune/1767299243.525676/events.out.tfevents.1767299243.admin---AgriEdgeX-Research.3517659.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d07e3d823f20fe9455c02119d179878e56d21c43e1be6eb5be86961afd34fd5
3
+ size 2846
logs/text2image-fine-tune/1767299243.5278287/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: 3
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: ButterChicken98/soyabean_bact_puls_plus_healthy_Qwen_Detailed
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 1
19
+ gradient_checkpointing: false
20
+ hub_model_id: soy_qwen_bact_v2
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: -1
27
+ logging_dir: logs
28
+ lr_scheduler: cosine
29
+ lr_warmup_steps: 500
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 5000
33
+ mixed_precision: fp16
34
+ noise_offset: 0.1
35
+ non_ema_revision: null
36
+ num_train_epochs: 29
37
+ offload_ema: false
38
+ output_dir: /home/svashistha/diffusion/output/soy_qwen/v1/bact
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: Manojb/stable-diffusion-2-1-base
41
+ push_to_hub: true
42
+ random_flip: true
43
+ report_to: all
44
+ resolution: 512
45
+ resume_from_checkpoint: latest
46
+ revision: null
47
+ scale_lr: false
48
+ seed: 42
49
+ snr_gamma: 5.0
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 8
52
+ train_data_dir: null
53
+ use_8bit_adam: false
54
+ use_ema: false
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1767299241.admin---AgriEdgeX-Research.3517659.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535aec3a395fd57f1c2385e455caeef05ca31a007d57ec8eafe2e2873ed1b273
3
+ size 2453577
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": false,
14
+ "safety_checker": [
15
+ null,
16
+ null
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "PNDMScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "dtype": "float16",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "transformers_version": "5.0.0.dev0",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
3
+ size 680820392
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|startoftext|>",
5
+ "do_lower_case": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "model_max_length": 77,
10
+ "pad_token": "!",
11
+ "tokenizer_class": "CLIPTokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f300063de8fcd9e9b36595bc7b7cdfa55b1094b8adc44667dc13f96e76a71f1e
3
+ size 3463726504
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Manojb/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 768,
28
+ "scaling_factor": 0.18215,
29
+ "shift_factor": null,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": true,
37
+ "use_quant_conv": true
38
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342
val_imgs_grid.png ADDED

Git LFS Details

  • SHA256: b09da2ead39e04de78bae98a4ca8ac09ad90a25001d032a67aed9961a2ba0211
  • Pointer size: 131 Bytes
  • Size of remote file: 406 kB